524 citations · 2.7k across the 55 of their papers we have counts for
7 papers · 1 filter
A Geometric Perspective on Self-Supervised Policy Adaptation
Cristian Bodnar, Karol Hausman, Gabriel Dulac-Arnold +1
One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what…
Confidence-rich grid mapping
Ali-akbar Agha-mohammadi, Eric Heiden, Karol Hausman +1
Representing the environment is a fundamental task in enabling robots to act autonomously in unknown environments. In this work, we present confidence-rich mapping (CRM), a new alg…
Modeling Long-horizon Tasks as Sequential Interaction Landscapes
Sören Pirk, Karol Hausman, Alexander Toshev +1
Complex object manipulation tasks often span over long sequences of operations. Task planning over long-time horizons is a challenging and open problem in robotics, and its complex…
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
Archit Sharma, Michael Ahn, Sergey Levine +3
Reinforcement learning provides a general framework for learning robotic skills while minimizing engineering effort. However, most reinforcement learning algorithms assume that a w…
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control
Ted Xiao, Eric Jang, Dmitry Kalashnikov +4
We study reinforcement learning in settings where sampling an action from the policy must be done concurrently with the time evolution of the controlled system, such as when a robo…
Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme +3
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potent…
Gradient Surgery for Multi-Task Learning
Tianhe Yu, Saurabh Kumar, Abhishek Gupta +3
While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, da…